---
title: eca_resnet33ts.ra2_in1k
canonical_url: "https://www.modelscope.cn/models/timm/eca_resnet33ts.ra2_in1k"
md_url: "https://www.modelscope.cn/models/timm/eca_resnet33ts.ra2_in1k.md"
repository: timm/eca_resnet33ts.ra2_in1k
last_updated: 2025-01-22
license: apache-2.0
pipeline_tag: image-classification
tasks:
  - image-classification
parameters: 19.7M
tensor_type:
  - I64
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 1814
stars: 0
tags:
  - image-classification
  - timm
  - transformers
---

# eca_resnet33ts.ra2_in1k

> eca_resnet33ts.ra2_in1k - timm 在 ModelScope 开源的模型。Model card for ecaresnet33ts.ra2in1k

timm/eca_resnet33ts.ra2_in1k 是 ModelScope 魔搭社区上的 19.7M 参数image-classification模型，采用 apache-2.0 许可。

- **Repository**: timm/eca_resnet33ts.ra2_in1k
- **License**: apache-2.0
- **Tasks**: image-classification
- **Parameters**: 19.7M
- **Tags**: image-classification, timm, transformers
- **Downloads**: 1814
- **Stars**: 0
- **Last updated**: 2025-01-22

Source: https://www.modelscope.cn/models/timm/eca_resnet33ts.ra2_in1k

---

# Model card for eca_resnet33ts.ra2_in1k

A ECA-ResNet image classification model (ResNet with 'Efficient Channel Attention'). This model features a tiered 3-layer stem without pooling and SiLU activations. Trained on ImageNet-1k by Ross Wightman in `timm`.

This model architecture is implemented using `timm`'s flexible [BYOBNet (Bring-Your-Own-Blocks Network)](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/byobnet.py).

BYOBNet allows configuration of:
 * block / stage layout
 * stem layout
 * output stride (dilation)
 * activation and norm layers
 * channel and spatial / self-attention layers

...and also includes `timm` features common to many other architectures, including:
 * stochastic depth
 * gradient checkpointing
 * layer-wise LR decay
 * per-stage feature extraction


## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
  - Params (M): 19.7
  - GMACs: 4.8
  - Activations (M): 11.7
  - Image size: train = 256 x 256, test = 288 x 288
- **Papers:**
  - ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks: https://arxiv.org/abs/1910.03151
  - @: a
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/huggingface/pytorch-image-models

## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model('eca_resnet33ts.ra2_in1k', pretrained=True)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1

top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```

### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model(
    'eca_resnet33ts.ra2_in1k',
    pretrained=True,
    features_only=True,
)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1

for o in output:
    # print shape of each feature map in output
    # e.g.:
    #  torch.Size([1, 32, 128, 128])
    #  torch.Size([1, 256, 64, 64])
    #  torch.Size([1, 512, 32, 32])
    #  torch.Size([1, 1536, 16, 16])
    #  torch.Size([1, 1280, 8, 8])

    print(o.shape)
```

### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model(
    'eca_resnet33ts.ra2_in1k',
    pretrained=True,
    num_classes=0,  # remove classifier nn.Linear
)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor

# or equivalently (without needing to set num_classes=0)

output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 1280, 8, 8) shaped tensor

output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```

## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).

## Citation
```bibtex
@misc{rw2019timm,
  author = {Ross Wightman},
  title = {PyTorch Image Models},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  doi = {10.5281/zenodo.4414861},
  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```
```bibtex
@InProceedings{wang2020eca,
  title={ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks},
  author={Qilong Wang, Banggu Wu, Pengfei Zhu, Peihua Li, Wangmeng Zuo and Qinghua Hu},
  booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020}
}
```
```bibtex
r
```
